知识大全 Java Lucene排重实现group by

Posted 2022-07-19 文字

篇首语：赋料扬雄敌，诗看子建亲。本文由小常识网(cha138.com)小编为大家整理，主要介绍了知识大全 Java Lucene排重实现group by相关的知识，希望对你有一定的参考价值。

Java Lucene排重实现group by  以下文字资料是由(全榜网网www.cha138.com)小编为大家搜集整理后发布的内容，让我们赶快一起来看一下吧！

　　package loongtao lucene test;

　　import java io IOException;

　　import apache lucene analysis standard StandardAnalyzer;

　　import apache lucene document Document;

　　import apache lucene document Field;

　　import apache lucene document Field Index;

　　import apache lucene document Field Store;

　　import apache lucene index CorruptIndexException;

　　import apache lucene index IndexWriter;

　　import apache lucene index Term;

　　import apache lucene index IndexWriter MaxFieldLength;

　　import apache lucene search DuplicateFilter;

　　import apache lucene search Filter;

　　import apache lucene search IndexSearcher;

　　import apache lucene search Query;

　　import apache lucene search ScoreDoc;

　　import apache lucene search TermQuery;

　　import apache lucene search TopDocs;

　　import apache lucene store Directory;

　　import apache lucene store LockObtainFailedException;

　　import apache lucene store RAMDirectory;

　　import apache lucene util Version;

　　public class DuplicateFilterTest

　　public static void main(String[] args)

　　Directory dir = new RAMDirectory();

　　Document doc = new Document();

　　doc add(new Field( id binbin Store YES Index NOT_ANALYZED));

　　doc add(new Field( string haha Store YES Index NOT_ANALYZED));

　　doc add(new Field( time Store YES Index NOT_ANALYZED));

　　doc add(new Field( duplicate Store YES Index NOT_ANALYZED));

　　Document doc = new Document();

　　doc add(new Field( id yaoyao Store YES Index NOT_ANALYZED));

　　doc add(new Field( string haha Store YES Index NOT_ANALYZED));

　　doc add(new Field( time Store YES Index NOT_ANALYZED));

　　doc

　　 add(new Field( duplicate Store YES

　　Index NOT_ANALYZED));

　　Document doc = new Document();

　　doc add(new Field( id zhangjian Store YES Index NOT_ANALYZED));

　　doc add(new Field( string haha Store YES Index NOT_ANALYZED));

　　doc add(new Field( time Store YES Index NOT_ANALYZED));

　　doc

　　 add(new Field( duplicate Store YES

　　Index NOT_ANALYZED));

　　Document doc = new Document();

　　doc add(new Field( id liweicheng Store YES Index NOT_ANALYZED));

　　doc add(new Field( string haha Store YES Index NOT_ANALYZED));

　　doc add(new Field( time Store YES Index NOT_ANALYZED));

　　doc

　　 add(new Field( duplicate Store YES

　　Index NOT_ANALYZED));

　　try

　　IndexWriter indexWriter = new IndexWriter(dir

　　new StandardAnalyzer(Version LUCENE_ ) true

　　MaxFieldLength LIMITED);

　　indexWriter addDocument(doc);

　　indexWriter addDocument(doc );

　　indexWriter addDocument(doc );

　　indexWriter addDocument(doc );

　　indexWriter close();

　　Query query = new TermQuery(new Term( string haha ));

　　Filter filter = new DuplicateFilter( duplicate );

　　IndexSearcher indexSearcher = new IndexSearcher(dir);

　　TopDocs top = indexSearcher search(query filter );

　　ScoreDoc[] scoreDocs = top scoreDocs;

　　for (ScoreDoc scoreDoc : scoreDocs)

　　Document rdoc = indexSearcher doc(scoreDoc doc);

　　System out print( id: +rdoc get( id ) +   排重ID: +rdoc get( duplicate ));

　　Query queryDuplicate = new TermQuery(new Term( duplicate rdoc get( duplicate )));

　　System out println( 转载: + indexSearcher search(queryDuplicate ) totalHits

　　);

　　 catch (CorruptIndexException e)

　　e printStackTrace();

　　 catch (LockObtainFailedException e)

　　e printStackTrace();

　　 catch (IOException e)

　　// TODO Auto generated catch block

　　e printStackTrace();

相关参考